← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
738.0
PP tok/s
52.0
TG tok/s
5550
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 711.6 | 54.8 | 66.3 GB | view |
| 4k | 738.0 | 52.0 | 66.7 GB | current |
| 8k | 722.6 | 48.8 | 67.0 GB | view |
| 16k | 677.6 | 8.7 | 86.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.8 | 1.00× |
| 2× | 56.7 | 1.03× |
| 4× | 89.1 | 1.63× |
| 8× | 42.5 | 0.78× |